Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    equation

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numbers (tokens containing decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Booking
    -0.06
    xae
    -0.06
    430
    -0.06
    .preferences
    -0.06
    	protected
    -0.06
     Sex
    -0.06
     foremost
    -0.06
    ่าส
    -0.06
     MOTOR
    -0.06
    asive
    -0.06
    POSITIVE LOGITS
    ($('<
    0.07
    鉄
    0.07
     Declarations
    0.07
     vám
    0.07
     adv
    0.06
    system
    0.06
    formation
    0.06
    (ع
    0.06
    ayım
    0.06
    ustum
    0.06
    Act Density 0.021%

    No Known Activations